Scheming Evals Mislead in Both Directions

·LessWrong··

We spent several weeks measuring in-context scheming, the behavior where a model covertly pursues a misaligned goal while outwardly appearing to comply, and the result that ended up surprising us had very little to do with whether models scheme and almost everything to do with whether we could believe our own instruments. Two of the behavioral detectors that this field routinely relies on gave us confidently wrong answers inside the same project, one of them by manufacturing a dramatic signal th...

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 6h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 1d ago
Harvard researchers find AI coding agents shifted the bottleneck to code review
judahmeek · Hacker News · 1d ago
New Evidence Shows School Phone Bans Are Gradually Improving Test Scores
donohoe · Hacker News · 1d ago
Java4Shell: RCE in OpenJDK when processing Base64
werrett · Hacker News · 1d ago